© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61435
    Prev
    Next
    INDEX
    Explanations

    patent claim related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lopen
    -0.08
    å¾Ģ常
    -0.07
    upert
    -0.07
    æĹłç¼ĺ
    -0.07
    azan
    -0.07
    egur
    -0.06
    ä¸ĸ家
    -0.06
    åĿĬ
    -0.06
    èĥĮæĻ¯ä¸ĭ
    -0.06
    eya
    -0.06
    POSITIVE LOGITS
    ingles
    0.08
     reiv
    0.07
     *__
    0.07
     patent
    0.07
    enho
    0.07
    à¸Ĺà¹īาย
    0.07
    çĹ¢
    0.07
    çķĮå®ļ
    0.07
    çŃīçĿĢ
    0.07
    -syntax
    0.07
    Activations Density 0.147%

    No Known Activations